检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wu, Wentao Hong, Fanghua Wang, Xiao Li, Chenglong Tang, Jin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation The School of Artificial Intelligence Anhui University Hefei230601 China School of Electronic and Information Engineering Anhui University Hefei230601 China School of Computer Science and Technology Anhui University Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230601 China

Existing vehicle detectors are usually obtained by training a typical detector (e.g., YOLO, RCNN, DETR series) on vehicle images based on a pre-trained backbone (e.g., ResNet, ViT). Some researchers also exploit and enhance the detection performance using pre-trained large foundation models. However, we think these detectors may only get sub-optimal results because the large models they use are not specifically designed for vehicles. In addition, their results heavily rely on visual features, and seldom of they consider the alignment between the vehicle's semantic information and visual representations. In this work, we propose a new vehicle detection paradigm based on a pre-trained foundation vehicle model (VehicleMAE) and a large language model (T5), termed VFM-Det. It follows the region proposal-based detection framework and the features of each proposal can be enhanced using VehicleMAE. More importantly, we propose a new VAtt2Vec module that predicts the vehicle semantic attributes of these proposals and transforms them into feature vectors to enhance the vision features via contrastive learning. Extensive experiments on three vehicle detection benchmark datasets thoroughly proved the effectiveness of our vehicle detector. Specifically, our model improves the baseline approach by +5.1%, +6.2% on the AP0.5, AP0.75 metrics, respectively, on the Cityscapes dataset. The source code of this work will be released at https://***/Event-AHU/VFM-Det. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Lessons for Theory from Scientific Domains Where Evidence is Sparse or Indirect

引用

computational Brain and Behavior 2024年第4期7卷 588-607页

作者： Woensdregt, Marieke Fusaroli, Riccardo Rich, Patricia Modrák, Martin Kolokolova, Antonina Wright, Cory Warlaumont, Anne S. Department of Cognitive Science and Artificial Intelligence Radboud University Nijmegen Netherlands Donders Institute for Brain Cognition and Behaviour Radboud University Nijmegen Netherlands Language and Computation in Neural Systems Max Planck Institute for Psycholinguistics Nijmegen Netherlands Department of Linguistics Cognitive Science and Semiotics School of Communication and Culture Aarhus University Aarhus Denmark Interacting Minds Center School of Culture and Society Aarhus University Aarhus Denmark Linguistic Data Consortium University of Pennsylvania Philadelphia PA United States Department of Philosophy University of Bayreuth Bayreuth Germany Institute of Microbiology of the Czech Academy of Sciences Prague Czech Republic Second Faculty of Medicine Charles University Prague Czech Republic Department of Computer Science Memorial University of Newfoundland St. John’s NL Canada Department of Philosophy California State University Long Beach Long Beach CA United States Department of Communication University of California Los Angeles Los Angeles CA United States

In many scientific fields, sparseness and indirectness of empirical evidence pose fundamental challenges to theory development. Theories of the evolution of human cognition provide a guiding example, where the targets of study are evolutionary processes that occurred in the ancestors of present-day humans. In many cases, the evidence is both very sparse and very indirect (e.g., archaeological findings regarding anatomical changes that might be related to the evolution of language capabilities);in other cases, the evidence is less sparse but still very indirect (e.g., data on cultural transmission in groups of contemporary humans and non-human primates). From examples of theoretical and empirical work in this domain, we distill five virtuous practices that scientists could aim to satisfy when evidence is sparse or indirect: (i) making assumptions explicit, (ii) making alternative theories explicit, (iii) pursuing computational and formal modelling, (iv) seeking external consistency with theories of related phenomena, and (v) triangulating across different forms and sources of evidence. Thus, rather than inhibiting theory development, sparseness or indirectness of evidence can catalyze it. To the extent that there are continua of sparseness and indirectness that vary across domains and that the principles identified here always apply to some degree, the solutions and advantages proposed here may generalise to other scientific domains. © The Author(s) 2024.

关键词： Cognitive science Evidence Explanation Theoretical virtues Theory development Underdetermination

来源：评论

学校读者我要写书评

暂无评论

Electroencephalogram and Event-Related Potential in Mild Cognitive Impairment: Recent Developments in Signal Processing, Machine Learning, and Deep Learning

IEEE Journal of Selected Areas in Sensors

引用

IEEE Journal of Selected Areas in Sensors 2025年 2卷 162-184页

作者： Azami, Hamed Mirjalili, Mina Rajji, Tarek K. Wu, Chien-Te Humeau-Heurtier, Anne Jung, Tzyy-Ping Wei, Chun-Shu Trinh, Thanh-Tung Liu, Yi-Hung University of Toronto Centre for Addiction and Mental Health TorontoONM5S 1A1 Canada University of Texas Southwestern Medical Center DallasTX75390 United States University of Florida Department of Occupational Therapy GainesvilleFL32611 United States University of Florida Center for Cognitive Aging and Memory McKnight Brain Institute GainesvilleFL32611 United States University of Angers LARIS SFR MATHSTIC AngersF-49000 France University of California Institute for Neural Computation Institute of Engineering in Medicine La Jolla CA92093 United States National Yang Ming Chiao Tung University Department of Computer Science Hsinchu City30010 Taiwan National Taipei University of Technology Graduate Institute of Manufacturing Technology College of Mechanical and Electrical Engineering Taipei10608 Taiwan Vietnam National University Department of Information and Communication Technology Faculty of Nontraditional Security HSB Hanoi720325 Viet Nam National Yang Ming Chiao Tung University Institute of Electrical and Control Engineering Hsinchu City30010 Taiwan

Mild cognitive impairment (MCI) is an early stage of non-age-related cognitive decline with an increased risk of progressing to dementia. Early detection of MCI is essential for implementing preventative strategies that can delay or prevent the onset of dementia, ultimately improving patient outcomes and reducing healthcare costs. Electroencephalograms (EEGs) and event-related potentials (ERPs) have shown significant promise in detecting MCI due to their affordability, real-time monitoring capabilities, and noninvasiveness. EEG provides continuous brain activity data, while ERPs offer insights into specific cognitive processes by analyzing brain responses to stimuli. These methods can complement each other in MCI diagnosis by providing a comprehensive view of overall brain function and detailed information on specific cognitive processes. However, EEG and ERP are susceptible to noise and interindividual variability, which can hinder their reliability. In addition, applying machine learning models on EEG or ERP for MCI detection presents challenges such as the risk of overfitting and difficulties in interpreting the underlying decision-making process. This review emphasizes recent advancements in signal processing and feature extraction methods applied to EEG and ERP data and explores the use of machine learning and deep learning techniques to enhance diagnostic accuracy and interpretative depth. By integrating these methodologies, the review highlights how EEG and ERP can contribute to a more effective understanding and monitoring of cognitive changes associated with MCI, underscoring the importance of early diagnosis for timely intervention and improved patient care. Finally, the review focuses on future research directions, including the development of advanced analytical techniques and multimodal integration approaches involving EEG and ERP to further improve diagnostic accuracy and clinical application. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A THEORY OF INITIALISATION’S IMPACT ON SPECIALISATION

arXiv

引用

arXiv 2025年

作者： Jarvis, Devon Lee, Sebastian Dominé, Clémentine Carla Juliette Saxe, Andrew M. Mannelli, Stefano Sarao School of Computer Science and Applied Mathematics University of the Witwatersrand South Africa Center for Computational Neuroscience Flatiron Institute Simons Foundation Gatsby Computational Neuroscience Unit Sainsbury Wellcome Centre UCL United Kingdom Data Science and AI Computer Science and Engineering Chalmers University of Technology University of Gothenburg Sweden Machine Intelligence and Neural Discovery Institute University of the Witwatersrand South Africa CIFAR Azrieli Global Scholar CIFAR

Prior work has demonstrated a consistent tendency in neural networks engaged in continual learning tasks, wherein intermediate task similarity results in the highest levels of catastrophic interference. This phenomenon is attributed to the network’s tendency to reuse learned features across tasks. However, this explanation heavily relies on the premise that neuron specialisation occurs, i.e. the emergence of localised representations. Our investigation challenges the validity of this assumption. Using theoretical frameworks for the analysis of neural networks, we show a strong dependence of specialisation on the initial condition. More precisely, we show that weight imbalance and high weight entropy can favour specialised solutions. We then apply these insights in the context of continual learning, first showing the emergence of a monotonic relation between task-similarity and forgetting in non-specialised networks. Finally, we show that specialization by weight imbalance is beneficial on the commonly employed elastic weight consolidation regularisation technique. Copyright © 2025, The Authors. All rights reserved.

关键词： neural networks

来源：评论

学校读者我要写书评

暂无评论

Consistency label-activated region generating network for weakly supervised medical image segmentation

引用

computers in Biology and Medicine 2024年 173卷 108380-108380页

作者： Du, Wei Huo, Yongkang Zhou, Rixin Sun, Yu Tang, Shiyi Zhao, Xuan Li, Ying Li, Gaoyang Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Changchun130012 China Translational Medical Center for Stem Cell Therapy and Institute for Regenerative Medicine Shanghai East Hospital Shanghai200092 China Bioinformatics Department School of Life Sciences and Technology Tongji University Shanghai200092 China

The current methods of auto-segmenting medical images are limited due to insufficient and ambiguous pathonmorphological labeling. In clinical practice, rough classification labels (such as disease or normal) are more commonly used than precise segmentation masks. However, there is still much to be explored regarding utilizing these weak clinical labels to accurately determine the lesion mask and guide medical image segmentation. In this paper, we proposed a weakly supervised medical image segmentation model to directly generate the lesion mask through a class activation map (CAM) guided cycle-consistency label-activated region transferring network. Cycle-consistency enforces that the mappings between the two domains should be reversible, which ensures that the original image can be reconstructed from the translated image. We developed a complementary branches fusion module to address the issue of blurry boundaries in CAM-guided segmentation. The complementary branch preserves the original semantic information of the non-lesion region and perfectly fuses the transferred feature of the lesion region with a complementary mask-constrained fake image generation process to clear the boundary of the lesion and non-lesion regions. This module allows the class transformation to focus solely on the label-activated region, resulting in more explicit segmentation. This model can accurately identify different region of medical images at the pixel-level while preserving the overall semantic structure semantion. It organizes disease labels and corresponding regions during image synthesis. Our method utilizes a joint discrimination strategy that significantly enhances the precision of the produced lesion mask. Extensive experiments of the proposed method on BraTs, ISIC and COVID-19 datasets demonstrate superior performance over existing state-of-the-art methods. The code and datasets are available at: https://***/mlcb-jlu/MedImgSeg. © 2024 Elsevier Ltd

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-based Non-Autoregressive Solver for Traveling Salesman Problems

arXiv

引用

arXiv 2023年

作者： Xiao, Yubin Wang, Di Li, Boyang Chen, Huanhuan Pang, Wei Wu, Xuan Li, Hao Xu, Dong Liang, Yanchun Zhou, You The Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education College of Computer Science and Technology Jilin University Changchun130012 China The Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly Nanyang Technological University 639798 Singapore The School of Computer Science and Engineering Nanyang Technological University 639798 Singapore The School of Computer Science University of Science & Technology of China Hefei230026 China The School of Mathematical and Computer Sciences Heriot-Watt University EdinburghEH14 4AS United Kingdom College of Computer National University of Defense Technology Hunan Changsha410073 China The Department of Electrical Engineering and Computer Science Bond Life Sciences Center University of Missouri Columbia United States The School of Computer Science Zhuhai College of Science and Technology Zhuhai519000 China

The Traveling Salesman Problem (TSP) is a well-known combinatorial optimization problem with broad real-world applications. Recently, neural networks have gained popularity in this research area because as shown in the literature, they provide strong heuristic solutions to TSPs. Compared to autoregressive neural approaches, non-autoregressive (NAR) networks exploit the inference parallelism to elevate inference speed but suffer from comparatively low solution quality. In this paper, we propose a novel NAR model named NAR4TSP, which incorporates a specially designed architecture and an enhanced reinforcement learning strategy. To the best of our knowledge, NAR4TSP is the first TSP solver that successfully combines RL and NAR networks. The key lies in the incorporation of NAR network output decoding into the training process. NAR4TSP efficiently represents TSP encoded information as rewards and seamlessly integrates it into reinforcement learning strategies, while maintaining consistent TSP sequence constraints during both training and testing phases. Experimental results on both synthetic and real-world TSPs demonstrate that NAR4TSP outperforms five state-of-the-art models in terms of solution quality, inference speed, and generalization to unseen scenarios. Copyright © 2023, The Authors. All rights reserved.

关键词： Traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

Contingency-aware influence maximization: A reinforcement learning approach

arXiv

引用

arXiv 2021年

作者： Chen, Haipeng Qiu, Wei Ou, Han-Ching An, Bo Tambe, Milind Center for Research on Computation and Society Harvard University School of Computer Science and Engineering Nanyang Technological University

The influence maximization (IM) problem aims at finding a subset of seed nodes in a social network that maximize the spread of influence. In this study, we focus on a sub-class of IM problems, where whether the nodes are willing to be the seeds when being invited is uncertain, called contingency-aware IM. Such contingency aware IM is critical for applications for non-profit organizations in low resource communities (e.g., spreading awareness of disease prevention). Despite the initial success, a major practical obstacle in promoting the solutions to more communities is the tremendous runtime of the greedy algorithms and the lack of high performance computing (HPC) for the non-profits in the field – whenever there is a new social network, the non-profits usually do not have the HPCs to recalculate the solutions. Motivated by this and inspired by the line of works that use reinforcement learning (RL) to address combinatorial optimization on graphs, we formalize the problem as a Markov Decision Process (MDP), and use RL to learn an IM policy over historically seen networks, and generalize to unseen networks with negligible runtime at test phase. To fully exploit the properties of our targeted problem, we propose two technical innovations that improve the existing methods, including state-abstraction and theoretically grounded reward shaping. Empirical results show that our method achieves influence as high as the state-of-the-art methods for contingency-aware IM, while having negligible runtime at test phase. © 2021, CC BY-NC-ND.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Identification Over Quantum Broadcast Channels

arXiv

引用

arXiv 2022年

作者： Rosenberger, Johannes Deppe, Christian Pereg, Uzi Technical University of Munich Germany School of Computation Information and Technology Department of Computer Engineering Germany Munich Center for Quantum Science and Technology Munich Germany Technion – Israel Institute of Technology Haifa Israel Helen Diller Quantum Center Department of Electrical and Computer Engineering

Identification over quantum broadcast channels is considered. As opposed to the information transmission task, the decoder only identifies whether a message of his choosing was sent or not. This relaxation allows for a double-exponential code size. An achievable identification region is derived for a quantum broadcast channel, and a full characterization for the class of classical-quantum broadcast channels. The identification capacity region of the single-mode pure-loss bosonic broadcast channel is obtained as a consequence. Furthermore, the results are demonstrated for the quantum erasure broadcast channel, where our region is suboptimal, but improves on the best previously known *** Codes 81P45 (Primary) 94A15, 94A40, 94A24 (Secondary) Copyright © 2022, The Authors. All rights reserved.

关键词： Bosons

来源：评论

学校读者我要写书评

暂无评论

A discussion of statistical criteria for assessing awareness with SMR BCI after brain injury

A discussion of statistical criteria for assessing awareness...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Idorenyin Amaunam Christoph Schneider Marina Lopes da Silva Jane Jöhr Karin Diserens Serafeim Perdikis Brain-Computer Interface and Neural Engineering Laboratory School of Computer Science and Electronic Engineering University of Essex Colchester United Kingdom Department of Radiology Gordon Center for Medical Imaging Massachusetts General Hospital Harvard Medical School Boston MA USA Department of Clinical Neurosciences Acute Neurorehabilitation Unit Division of Neurology Centre Hospitalier Universitaire Vaudois Lausanne Switzerland

This work discusses the implications of selecting particular statistical metrics and thresholds as criteria to diagnose awareness through Brain-computer Interface (BCI) technology in patients with Disorders of Consciousness (DOC). We report a first analysis of a novel dataset collected to investigate whether a motor attempt electroencephalography (EEG) paradigm coupled with Functional Electrical Stimulation (FES) can detect command following and, therefore, signs of conscious awareness in DOC. We assessed 22 DOC patients admitted to the acute rehabilitation unit after a brain lesion over one or more sessions. We extracted EEG sensorimotor rhythms and performed a standard open-loop BCI pipeline evaluation, classifying motor attempt against resting-state trials. We validate this approach by correlating classification accuracy with the established clinical scale Coma Recovery Scale Revised. We employ a machine learning (ML)-inspired diagnostic criterion based on confidence intervals over chance-level classification accuracy and show that it yields more conservative and, arguably, reliable inference of Cognitive Motor Dissociation (CMD) by means of command-following, neuroimaging-based tools, compared to diagnoses based on clinical assessments or criteria examining the statistical significance of brain features across different mental states.

关键词：

来源：评论

学校读者我要写书评

暂无评论

neural Network Student Cognitive Diagnosis Model Based on Multi-Relational Graph 25

Neural Network Student Cognitive Diagnosis Model Based on Mu...

引用

Proceedings of the 2025 2nd International Conference on Generative Artificial Intelligence and Information Security

作者： Ze Han Yu Su Qi Mo Xinyu Nie School of Electronic and Information Engineering Anhui University Hefei Anhui China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Hefei Anhui China School of Computer Science and Artificial Intelligence Hefei Normal University Hefei Anhui China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei Anhui China AHU-IAI AI Joint Laboratory Anhui University Hefei Anhui China School of Electronic and Information Engineering Anhui University Hefei Anhui China

ISBN: (纸本)9798400713453

The Internet has enabled online learning to become an important means for students to acquire knowledge, and student cognitive diagnosis models have played a key role in this process. These models can evaluate students' learning behaviors and knowledge mastery, providing support for personalized learning. Unfortunately, traditional models have their limitations when dealing with complex relational data related mainly to the relationship between students and problems, while the characteristics as well as potential relationships among students are almost left neglected. In response, this paper proposes a neural Network Student Cognitive Diagnosis Model Based on Multi-Relational Graph (MGNCD) that brings together the powers of Graph Attention Network (GAT) and Relational Graph Convolutional Network (RGCN) to model multi-dimensional heterogeneous nodes such as students, classes, problems, and skills. The introduction of various edge types and random edge connection strategies allowed the model to tackle data sparsity and heterogeneity. Experimental results indicate that the proposed model outperforms traditional methods in accuracy (ACC) and area under the curve (AUC), which provides an encouraging novel insight into cognitive diagnosis.

关键词： Cognitive diagnosis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：